NeRF-Texture: Synthesizing Neural Radiance Field Textures

TL;DR

This paper introduces NeRF-Texture, a novel method for synthesizing 3D scene textures with meso-structure by disentangling shape and texture, enabling realistic multi-view texture generation over complex surfaces.

Contribution

The paper proposes a new NeRF-based texture synthesis approach that models meso-structure textures on 3D shapes, improving over traditional 2D methods by handling complex geometries and view-dependent appearances.

Findings

Effective synthesis of textures with meso-structure on 3D shapes.

Ability to generate textures on curved surfaces.

Regularization improves latent feature matching quality.

Abstract

Texture synthesis is a fundamental problem in computer graphics that would benefit various applications. Existing methods are effective in handling 2D image textures. In contrast, many real-world textures contain meso-structure in the 3D geometry space, such as grass, leaves, and fabrics, which cannot be effectively modeled using only 2D image textures. We propose a novel texture synthesis method with Neural Radiance Fields (NeRF) to capture and synthesize textures from given multi-view images. In the proposed NeRF texture representation, a scene with fine geometric details is disentangled into the meso-structure textures and the underlying base shape. This allows textures with meso-structure to be effectively learned as latent features situated on the base shape, which are fed into a NeRF decoder trained simultaneously to represent the rich view-dependent appearance. Using this implicit representation, we can synthesize NeRF-based textures through patch matching of latent features. However, inconsistencies between the metrics of the reconstructed content space and the latent feature space may compromise the synthesis quality. To enhance matching performance, we further regularize the distribution of latent features by incorporating a clustering constraint. In addition to generating NeRF textures over a planar domain, our method can also synthesize NeRF textures over curved surfaces, which are practically useful. Experimental results and evaluations demonstrate the effectiveness of our approach.